| CPC G06V 20/52 (2022.01) [G06V 10/72 (2022.01); H04N 7/181 (2013.01); H04N 23/661 (2023.01); H04W 4/20 (2013.01); H04W 88/16 (2013.01)] | 15 Claims |
|
1. A method, comprising:
dividing a location into a plurality of areas, each of the plurality of areas associated with one or more candidate tasks;
recognizing, from sensor data, an area from the plurality of areas and a candidate task from the one or more candidate tasks associated with the area;
estimating a probability of each of the plurality of candidate tasks for the each of the plurality of areas for a specific future period of time, based on referencing historical data of task sequences previously executed;
accepting ones of the plurality of candidate tasks for the each of the plurality of areas having the probability being higher than a threshold; and
for the each of the plurality of areas not having the probability being higher than the threshold, activating one or more sensors and transmitting sensor data received from the one or more sensors in the specific future period of time in associated areas for the plurality of areas associated with other ones of the plurality of candidate tasks,
wherein the estimating the probability of each of the plurality of candidate tasks for the each of the plurality of areas for a specific future period of time, based on referencing historical data of task sequences previously executed comprises computing a sequence probability of one or more current task sequences from the plurality of candidate tasks based on the referencing of the historical data of task sequences previously executed;
wherein the accepting the ones of the plurality of candidate tasks for the each of the plurality of areas having the probability being higher than a threshold comprises computing a current task duration and a current task sequence from the one or more current task sequences from the accepted ones of the plurality of candidate tasks and storing the current task duration and the current task sequence into a database.
|